Korean Morphological Analysis with Tied Sequence-to-Sequence Multi-Task Model

Korean morphological analysis has been considered as a sequence of morpheme processing and POS tagging. Thus, a pipeline model of the tasks has been adopted widely by previous studies. However, the model has a problem that it cannot utilize interactions among the tasks. This paper formulates Korean morphological analysis as a combination of the tasks and presents a tied sequence-to-sequence multi-task model for training the two tasks simultaneously without any explicit regularization. The experiments prove the proposed model achieves the state-of-the-art performance.

[1]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jihun Choi,et al.  A grapheme-level approach for constructing a Korean morphological analyzer without linguistic knowledge , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[3]  Dianhai Yu,et al.  Multi-Task Learning for Multiple Language Translation , 2015, ACL.

[4]  Hae-Chang Rim,et al.  Probabilistic Modeling of Korean Morphology , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  Christopher D. Manning.  Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics? , 2011, CICLing.

[6]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[7]  Josef van Genabith,et al.  Neural Morphological Tagging from Characters for Morphologically Rich Languages , 2016, ArXiv.

[8]  Young-Bum Kim,et al.  Rich Character-Level Information for Korean Morphological Analysis and Part-of-Speech Tagging , 2018, COLING.

[9]  Quoc V. Le,et al.  Multi-task Sequence to Sequence Learning , 2015, ICLR.

[10]  Seong-Bae Park,et al.  Korean Part-of-speech Tagging Based on Morpheme Generation , 2020, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[11]  David Chiang,et al.  Tied Multitask Learning for Neural Speech Translation , 2018, NAACL.

[12]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[13]  Xuanjing Huang,et al.  A Feature-Enriched Neural Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging , 2016, IJCAI.

[14]  Jörg Tiedemann,et al.  Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF , 2017, IJCNLP.

[15]  Stephen Clark,et al.  Joint Word Segmentation and POS Tagging Using a Single Perceptron , 2008, ACL.

[16]  Wei Xu,et al.  Bidirectional LSTM-CRF Models for Sequence Tagging , 2015, ArXiv.

[17]  Seung-Hoon Na,et al.  Conditional Random Fields for Korean Morpheme Segmentation and POS Tagging , 2015, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[18]  Dan Klein,et al.  Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network , 2003, NAACL.

[19]  Jae Jung Song,et al.  THE KOREAN LANGUAGE: Structure, use and context , 2005 .

[20]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[21]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.